We’re going to cover:

Regression related:

Advanced Regressions

Panel Data

There are a few packages out there that implement panel data models. We’ll cover two of them, plm() - an older frequently used package, and a newer package, fixest(). Another package to note is lfe.

Fixed Effects Models

Fixed effects models are equivalent to including dummy variables for the entity that you are following over time. You can include these dummy variables as factors (either for time or entity). However, that is computationally inefficient if you have some 1,500 people, for example. So, instead, we use the within transformation.

In plm() is an option for “within” - that is the fixed effects model. This is because you are taking differences within an entity.

Let’s use world bank data to apply the fixed effects model.

library("WDI")
library("tidyverse")
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.0 ──
## ✔ ggplot2 3.4.2     ✔ purrr   1.0.1
## ✔ tibble  3.2.1     ✔ dplyr   1.1.1
## ✔ tidyr   1.3.0     ✔ stringr 1.5.0
## ✔ readr   2.1.4     ✔ forcats 1.0.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
wdi <- WDI(country = "all", start=2000, end=2020, extra="TRUE",
           indicator=c("NY.GDP.MKTP.KD.ZG","SL.TLF.CACT.FE.ZS","SP.POP.TOTL", "SE.PRM.CUAT.ZS" ))

Let’s quickly clean this up a bit by renaming the columns. I’m going to leave in unnecessary columns since the data is not very large, but if I was working with a large dataframe, I’d drop it.

wdi <- rename(wdi,  gdp= NY.GDP.MKTP.KD.ZG, lfpart_f= SL.TLF.CACT.FE.ZS, pop= SP.POP.TOTL, edu = SE.PRM.CUAT.ZS)

names(wdi)
##  [1] "iso2c"     "country"   "year"      "gdp"       "lfpart_f"  "pop"      
##  [7] "edu"       "iso3c"     "region"    "capital"   "longitude" "latitude" 
## [13] "income"    "lending"

Let’s great a baseline model regression with OLS:

ols <- lm(gdp~edu + log(pop), data=wdi)

Now, let’s run our model.

We need to tell plm what entity is being followed and what is the variable for time using the option index, and we need to tell plm what kind of model we are running.

Typically, the function is a class of regression methods and there will be an option for a specific estimation model. plm can be considered a package for panel data models and the estimation model is “within”

A one-way fixed effects model is like this:

library("plm")
## 
## Attaching package: 'plm'
## The following objects are masked from 'package:dplyr':
## 
##     between, lag, lead
fixed <- plm(gdp~  edu + log(pop) , data=wdi, index = c("iso2c"), model="within")

summary(fixed)
## Oneway (individual) effect Within Model
## 
## Call:
## plm(formula = gdp ~ edu + log(pop), data = wdi, model = "within", 
##     index = c("iso2c"))
## 
## Unbalanced Panel: n = 154, T = 1-21, N = 847
## 
## Residuals:
##     Min.  1st Qu.   Median  3rd Qu.     Max. 
## -17.3968  -1.0948   0.2940   1.6537  19.1790 
## 
## Coefficients:
##            Estimate Std. Error t-value  Pr(>|t|)    
## edu       -0.109002   0.038462 -2.8341   0.00473 ** 
## log(pop) -10.776449   1.882798 -5.7236 1.554e-08 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Total Sum of Squares:    10661
## Residual Sum of Squares: 9432.5
## R-Squared:      0.11523
## Adj. R-Squared: -0.083237
## F-statistic: 44.9963 on 2 and 691 DF, p-value: < 2.22e-16
#equivalent in stata:
#xtset iso2c year
#xtreg gdp edu lnpop, fe

But, we can include fixed effects for time, too. We just need to include it in the index.

fixed <- plm(gdp~ edu + log(pop) , data=wdi, index = c("iso2c", "year"), model="within")
summary(fixed)
## Oneway (individual) effect Within Model
## 
## Call:
## plm(formula = gdp ~ edu + log(pop), data = wdi, model = "within", 
##     index = c("iso2c", "year"))
## 
## Unbalanced Panel: n = 154, T = 1-21, N = 847
## 
## Residuals:
##     Min.  1st Qu.   Median  3rd Qu.     Max. 
## -17.3968  -1.0948   0.2940   1.6537  19.1790 
## 
## Coefficients:
##            Estimate Std. Error t-value  Pr(>|t|)    
## edu       -0.109002   0.038462 -2.8341   0.00473 ** 
## log(pop) -10.776449   1.882798 -5.7236 1.554e-08 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Total Sum of Squares:    10661
## Residual Sum of Squares: 9432.5
## R-Squared:      0.11523
## Adj. R-Squared: -0.083237
## F-statistic: 44.9963 on 2 and 691 DF, p-value: < 2.22e-16

We can see the number of observations (N), the number of groups (n), how many units you have over time (T).

If you want to see the fixedeffects estimtates, you can do this with fixef()

fixef(fixed)
##     AD     AE     AL     AM     AO     AR     AU     AW     AZ     BA     BB 
## 136.36 183.14 175.71 174.78 194.07 199.57 196.32 135.81 188.59 172.78 148.42 
##     BD     BE     BF     BG     BH     BI     BN     BO     BR     BS     BT 
## 215.46 186.32 185.73 185.70 162.16 178.49 152.74 181.98 216.21 150.91 153.38 
##     BY     BZ     CA     CD     CH     CI     CL     CM     CO     CR     CU 
## 184.71 142.66 198.46 207.74 183.93 195.93 193.17 187.96 201.71 177.80 186.83 
##     CV     CW     CY     CZ     DE     DK     DM     DO     DZ     EC     EE 
## 149.15 121.18 161.97 187.56 208.33 178.33 129.62 186.68 195.95 189.45 167.84 
##     EG     ES     ET     FJ     FR     GB     GE     GH     GL     GM     GN 
## 208.42 200.31 211.02 155.81 205.82 204.23 178.78 198.76 130.19 165.90 182.53 
##     GR     GT     GY     HK     HN     HR     HU     ID     IL     IN     IQ 
## 184.29 185.86 154.42 183.20 182.85 176.34 186.69 221.42 185.32 234.44 203.63 
##     IT     JO     JP     KE     KG     KH     KR     KW     KY     KZ     LB 
## 202.30 183.93 216.12 200.46 180.59 187.22 205.72 171.16 130.48 194.77 183.67 
##     LI     LK     LS     LT     LU     LV     MD     ME     MG     MH     MK 
## 125.89 188.38 166.31 174.56 159.43 169.25 174.41 157.02 192.88 127.42 163.68 
##     ML     MM     MN     MO     MR     MT     MU     MV     MX     MY     MZ 
## 185.78 205.35 171.15 160.59 170.58 155.53 163.49 166.77 209.93 199.44 193.39 
##     NA     NE     NG     NL     NO     NP     OM     PA     PE     PF     PH 
## 162.18 192.06 215.01 190.83 178.89 192.07 171.27 175.43 199.39 145.56 213.28 
##     PK     PL     PR     PS     PT     PW     PY     QA     RO     RS     RU 
## 215.00 201.27 172.56 178.37 184.10 112.83 179.00 173.87 195.17 182.95 217.89 
##     RW     SA     SC     SE     SG     SI     SK     SL     SM     SN     SR 
## 186.68 195.52 133.63 186.30 180.34 169.29 180.69 176.31 124.52 182.24 157.41 
##     ST     SV     SY     TD     TG     TH     TJ     TO     TR     TT     TZ 
## 143.72 175.90 192.65 194.37 179.17 205.70 187.59 142.15 210.12 162.28 201.07 
##     UA     UG     US     UY     UZ     VC     VE     VN     WS     ZA     ZW 
## 210.14 196.31 223.16 174.85 203.08 136.27 198.59 215.07 147.30 202.44 188.27

fixest

You can run the same above regression with the package fixest using the function feols(). I’m mentioning this particular package because it is insanely fast. It can handle a huge amount of fixed effects where stata might break (unless you use reghdfe). It can support non-linear models, high-dimensional fixed effects, multiway clustering and a bunch of options that come in handy when you work with detailed data or big data. So, I want you to know it exists because of it’s flexibility in all things fixed effects.

Let’s try it. Rather than setting the fixed effects with an index, you’ll include the variables that are fixed after |

Let’s see what I mean here:

library("fixest")

fixed_est = feols(gdp~  edu + log(pop) | country + year, data = wdi)  ## Fixed effect(s) go after the "|"
## NOTE: 4,739 observations removed because of NA values (LHS: 301, RHS: 4,733).
fixed_est
## OLS estimation, Dep. Var.: gdp
## Observations: 847 
## Fixed-effects: country: 154,  year: 21
## Standard-errors: Clustered (country) 
##           Estimate Std. Error   t value Pr(>|t|)    
## edu      -0.012566   0.049167 -0.255574 0.798623    
## log(pop) -6.210177   2.885516 -2.152189 0.032951 *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## RMSE: 2.63618     Adj. R2: 0.540777
##                 Within R2: 0.025765

Standard errors are already clustered by country automatically, but if you want standard errors, you can do so using summary and the option se

summary(fixed_est, se = 'standard')
## OLS estimation, Dep. Var.: gdp
## Observations: 847 
## Fixed-effects: country: 154,  year: 21
## Standard-errors: IID 
##           Estimate Std. Error   t value   Pr(>|t|)    
## edu      -0.012566   0.034788 -0.361215 0.71805249    
## log(pop) -6.210177   1.648087 -3.768111 0.00017896 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## RMSE: 2.63618     Adj. R2: 0.540777
##                 Within R2: 0.025765

There might be time where you want to cluster your standard errors with specific items. You can also specify what you would like to cluster with the option cluster

summary(fixed_est, cluster = c('iso2c'))
## OLS estimation, Dep. Var.: gdp
## Observations: 847 
## Fixed-effects: country: 154,  year: 21
## Standard-errors: Clustered (iso2c) 
##           Estimate Std. Error   t value Pr(>|t|)    
## edu      -0.012566   0.049167 -0.255574 0.798623    
## log(pop) -6.210177   2.885516 -2.152189 0.032951 *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## RMSE: 2.63618     Adj. R2: 0.540777
##                 Within R2: 0.025765

Random Effects Models

For plm, changing to a random effect model is pretty simple. You just need to change the option “model” to “random”

re <- plm(gdp~edu + log(pop), data=wdi, index = c("iso2c"), model="random")
summary(re)
## Oneway (individual) effect Random Effect Model 
##    (Swamy-Arora's transformation)
## 
## Call:
## plm(formula = gdp ~ edu + log(pop), data = wdi, model = "random", 
##     index = c("iso2c"))
## 
## Unbalanced Panel: n = 154, T = 1-21, N = 847
## 
## Effects:
##                  var std.dev share
## idiosyncratic 13.651   3.695 0.816
## individual     3.085   1.756 0.184
## theta:
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
## 0.09686 0.34849 0.46440 0.41390 0.50994 0.58282 
## 
## Residuals:
##     Min.  1st Qu.   Median     Mean  3rd Qu.     Max. 
## -18.9027  -1.4822   0.2145   0.0005   1.7886  23.4209 
## 
## Coefficients:
##               Estimate Std. Error z-value  Pr(>|z|)    
## (Intercept) 10.8735302  2.1454855  5.0681 4.018e-07 ***
## edu         -0.0701905  0.0094268 -7.4459 9.630e-14 ***
## log(pop)    -0.1175837  0.1160379 -1.0133    0.3109    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Total Sum of Squares:    13907
## Residual Sum of Squares: 12666
## R-Squared:      0.089208
## Adj. R-Squared: 0.08705
## Chisq: 55.6859 on 2 DF, p-value: 8.0902e-13

There is something else called a mixed model where you might have both fixed effects and random effect parameters. This is particularly useful for nested datasets and when you might want to include fixed effects at one level and random effects for another variable. I’ve rarely seen it in economics papers, but it is often included in psychology models. I won’t discuss this indepthly, but here is a website that explains how to apply it in R - although there are many out there and often people use the package lmer().

Hausman Taylor test

You may know that when deciding between random or fixed effects models, you have to ensure that the random variables do not correlate with your independent variables. Frequently, this assumption is broken and is why most people use fixed effects models. However, we often want to test between our fixed or random effect model. We do this with the phtest() function in plm.

fe <- plm(gdp ~ edu +log(pop) , data=wdi, index = c("iso2c"), model="within")

summary(fe)
## Oneway (individual) effect Within Model
## 
## Call:
## plm(formula = gdp ~ edu + log(pop), data = wdi, model = "within", 
##     index = c("iso2c"))
## 
## Unbalanced Panel: n = 154, T = 1-21, N = 847
## 
## Residuals:
##     Min.  1st Qu.   Median  3rd Qu.     Max. 
## -17.3968  -1.0948   0.2940   1.6537  19.1790 
## 
## Coefficients:
##            Estimate Std. Error t-value  Pr(>|t|)    
## edu       -0.109002   0.038462 -2.8341   0.00473 ** 
## log(pop) -10.776449   1.882798 -5.7236 1.554e-08 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Total Sum of Squares:    10661
## Residual Sum of Squares: 9432.5
## R-Squared:      0.11523
## Adj. R-Squared: -0.083237
## F-statistic: 44.9963 on 2 and 691 DF, p-value: < 2.22e-16
phtest(fe, re)
## 
##  Hausman Test
## 
## data:  gdp ~ edu + log(pop)
## chisq = 63.493, df = 2, p-value = 1.632e-14
## alternative hypothesis: one model is inconsistent

There are a variety of tests for serial correlation, heteroskedasticity, random effects (if you should include random effects compared to an ols model, stationarity/unit roots, etc). These are outlined in the vignettes of plm and you can explore them further on your own.

Logit/Probit

Logit/probit models can be run using the generalized linear model packages glm() You identify a logit or probit model using the option “family”. You need to specify the link function to distinguish between a logit or probit model.

A good introduction to logit models (and many other applied econometric models) can be found at UCLA’s website here and for probit models here

Let’s start with a logit model:

setwd("/Users/mkaltenberg/Documents/GitHub/Data_Analysis_Python_R/Advanced Regressions Stargazer/")
smoking <- read.csv("smoking.csv")
names(smoking)
##  [1] "smoker"   "smkban"   "age"      "hsdrop"   "hsgrad"   "colsome" 
##  [7] "colgrad"  "black"    "hispanic" "female"
logit <- glm(smoker ~ age + female + hsdrop +hsgrad +colsome +colgrad, data = smoking, family = "binomial")
summary(logit)
## 
## Call:
## glm(formula = smoker ~ age + female + hsdrop + hsgrad + colsome + 
##     colgrad, family = "binomial", data = smoking)
## 
## Deviance Residuals: 
##     Min       1Q   Median       3Q      Max  
## -1.0622  -0.8203  -0.5884  -0.4056   2.2899  
## 
## Coefficients:
##              Estimate Std. Error z value Pr(>|z|)    
## (Intercept) -1.940401   0.135308 -14.341  < 2e-16 ***
## age         -0.005998   0.001964  -3.054 0.002256 ** 
## female      -0.210057   0.048467  -4.334 1.46e-05 ***
## hsdrop       1.771164   0.126802  13.968  < 2e-16 ***
## hsgrad       1.521847   0.113672  13.388  < 2e-16 ***
## colsome      1.161500   0.116063  10.007  < 2e-16 ***
## colgrad      0.424145   0.125638   3.376 0.000736 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 11074  on 9999  degrees of freedom
## Residual deviance: 10583  on 9993  degrees of freedom
## AIC: 10597
## 
## Number of Fisher Scoring iterations: 4

The probit model just needs a tweak in the link function within the option “family”, and that is set like this:

probit <- glm(smoker ~ age + female + hsdrop +hsgrad +colsome +colgrad, data = smoking, family = binomial(link = "probit"))
summary(probit)
## 
## Call:
## glm(formula = smoker ~ age + female + hsdrop + hsgrad + colsome + 
##     colgrad, family = binomial(link = "probit"), data = smoking)
## 
## Deviance Residuals: 
##     Min       1Q   Median       3Q      Max  
## -1.0563  -0.8214  -0.5919  -0.4005   2.3070  
## 
## Coefficients:
##              Estimate Std. Error z value Pr(>|z|)    
## (Intercept) -1.125266   0.073137 -15.386  < 2e-16 ***
## age         -0.003458   0.001157  -2.990 0.002791 ** 
## female      -0.123336   0.028445  -4.336 1.45e-05 ***
## hsdrop       1.005005   0.068663  14.637  < 2e-16 ***
## hsgrad       0.851358   0.059047  14.418  < 2e-16 ***
## colsome      0.637198   0.060379  10.553  < 2e-16 ***
## colgrad      0.220119   0.064848   3.394 0.000688 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 11074  on 9999  degrees of freedom
## Residual deviance: 10584  on 9993  degrees of freedom
## AIC: 10598
## 
## Number of Fisher Scoring iterations: 4

Marginal effects can’t be read directly from the output. You need to apply the link function to interpret the results (though the sign and standard error can be interpreted as usual).

This is why the margins function is so important! Margins works with other regressions, as well.

Margins

The margins package is quite similar to the margins package in STATA. You can apply interpretation to a wide variety of regressions - logit/probit, but also non-linear terms in OLS models. You can check out more examples and features in its vignette here.

The package makes it easy to calculate values and plot them.

When we use margins(model_name) it will give us the average marginal effect for each variable

library(margins)

logit_m <-margins(logit)

And we can plot it quit easily:

plot(logit_m)

To get the partial effect at the mean (or at any particular value), we us the at option:

Here we specify a range of numbers

margins(logit, at = list(age = c(18,40,60)), variables = "age")

Or at the mean of age

mean_age = mean(smoking$age, na.rm=TRUE)

margins(logit, at = list(age = c(mean(smoking$age, na.rm=TRUE))), variables = "age")

Marignal effects for non-linear terms in OLS

The margins package can also be used to get the marginal effects for non-linear terms in OLS models - often these are interactions or polynomial functions. Let’s take an example of a model with the squared term population.

Notice that to square a term I use “^2” and the “I()” to indicate that it’s a second order term.

int <- lm(gdp ~ lfpart_f + pop + I(pop^2), data = wdi)
summary(int)
## 
## Call:
## lm(formula = gdp ~ lfpart_f + pop + I(pop^2), data = wdi)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -57.690  -1.887   0.170   2.271  83.751 
## 
## Coefficients:
##               Estimate Std. Error t value Pr(>|t|)    
## (Intercept)  2.616e+00  2.665e-01   9.814  < 2e-16 ***
## lfpart_f     1.335e-02  5.083e-03   2.626  0.00866 ** 
## pop          1.188e-09  2.079e-10   5.713 1.18e-08 ***
## I(pop^2)    -1.614e-19  3.826e-20  -4.218 2.51e-05 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 5.099 on 4801 degrees of freedom
##   (781 observations deleted due to missingness)
## Multiple R-squared:  0.009764,   Adjusted R-squared:  0.009145 
## F-statistic: 15.78 on 3 and 4801 DF,  p-value: 3.288e-10

Let’s apply marginal effect to population. We can take the marginal effect of any particular value of population that we are interested in.

# in python wdi['pop']

m_pop <- mean(wdi$pop, na.rm=TRUE)  # getting the mean of population

margins(int, at = list(pop =m_pop))

We can combine those two lines of code into one (and not save the value of the mean of population that will take up RAM)

margins(int, at = list(pop = mean(wdi$pop, na.rm=TRUE)))

We can input a list of values rather than just one value

margins(int, at = list(pop = c(1000000,5000000, 9000000)))

It’s far better to use numbers relevant to the value/data that exists. We can use a bunch of summary statistics instead of just one to see the marginal effects of population. Turkey’s 5 numbers include min, lower hinge, median, upper hinge and maximum - the function is called fivenum()

Looking at the marginal effects, you can see that the labor force participation of women is constant (as expected), but population marginal effects depend on the value of population - there seems to be a non-linear relationship.

fivenum(wdi$pop, na.rm= TRUE)  # This is how to get the statistics
## [1]       9609    1440729    9458989   59095365 7820981524
margins(int, at = list(pop =fivenum(wdi$pop, na.rm= TRUE)))  #integrated within margins command
## Warning in check_values(data, at): A 'at' value for 'pop' is outside observed
## data range (102603,7820981524)!

And we can also graph the marginal effect of population with cplot()

cplot(int, "pop", what = "effect", main = "Average Marginal Effect of Population")

Stargazer (Again)

Let’s show some models side by side

library(stargazer)
## 
## Please cite as:
##  Hlavac, Marek (2018). stargazer: Well-Formatted Regression and Summary Statistics Tables.
##  R package version 5.2.2. https://CRAN.R-project.org/package=stargazer
knitr::opts_chunk$set(echo = TRUE, warning = FALSE)

stargazer(ols, re, fe, type = "html", column.labels = c("OLS", "RE", "FE"), model.names = FALSE,
          dep.var.caption = "",
          title            = "Panel Data Results",
          covariate.labels = c("Edu", "lnPop", "Constant"),
          dep.var.labels   = "GDP per capita",
          add.lines=list(c("FE", "No", "No", "Yes")),
          out = "panel_results.html")
## 
## <table style="text-align:center"><caption><strong>Panel Data Results</strong></caption>
## <tr><td colspan="4" style="border-bottom: 1px solid black"></td></tr><tr><td style="text-align:left"></td><td colspan="3">GDP per capita</td></tr>
## <tr><td style="text-align:left"></td><td>OLS</td><td>RE</td><td>FE</td></tr>
## <tr><td style="text-align:left"></td><td>(1)</td><td>(2)</td><td>(3)</td></tr>
## <tr><td colspan="4" style="border-bottom: 1px solid black"></td></tr><tr><td style="text-align:left">Edu</td><td>-0.060<sup>***</sup></td><td>-0.070<sup>***</sup></td><td>-0.109<sup>***</sup></td></tr>
## <tr><td style="text-align:left"></td><td>(0.007)</td><td>(0.009)</td><td>(0.038)</td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">lnPop</td><td>-0.185<sup>**</sup></td><td>-0.118</td><td>-10.776<sup>***</sup></td></tr>
## <tr><td style="text-align:left"></td><td>(0.082)</td><td>(0.116)</td><td>(1.883)</td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">Constant</td><td>11.164<sup>***</sup></td><td>10.874<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td>(1.570)</td><td>(2.145)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td></tr>
## <tr><td colspan="4" style="border-bottom: 1px solid black"></td></tr><tr><td style="text-align:left">FE</td><td>No</td><td>No</td><td>Yes</td></tr>
## <tr><td style="text-align:left">Observations</td><td>847</td><td>847</td><td>847</td></tr>
## <tr><td style="text-align:left">R<sup>2</sup></td><td>0.078</td><td>0.089</td><td>0.115</td></tr>
## <tr><td style="text-align:left">Adjusted R<sup>2</sup></td><td>0.075</td><td>0.087</td><td>-0.083</td></tr>
## <tr><td style="text-align:left">Residual Std. Error</td><td>4.203 (df = 844)</td><td></td><td></td></tr>
## <tr><td style="text-align:left">F Statistic</td><td>35.492<sup>***</sup> (df = 2; 844)</td><td>55.686<sup>***</sup></td><td>44.996<sup>***</sup> (df = 2; 691)</td></tr>
## <tr><td colspan="4" style="border-bottom: 1px solid black"></td></tr><tr><td style="text-align:left"><em>Note:</em></td><td colspan="3" style="text-align:right"><sup>*</sup>p<0.1; <sup>**</sup>p<0.05; <sup>***</sup>p<0.01</td></tr>
## </table>

Let’s see how we can only show covariates of interest so that our table is reasonable.

Here is the ugly table that you won’t show me because it’s unreasonable, right?

knitr::opts_chunk$set(echo = TRUE, warning = FALSE)

#long version 
fe_ols = lm(gdp~  edu + log(pop) +factor(country) +factor(year), data = wdi, na.action = na.omit)  ## Fixed effect(s)

#notice that the coefficients aren't the same. That's because of the way lm() handles missing data. It's better to use plm then factor with lm. 

#Here is another way to calculate FE
fe_plm <- plm(gdp~  edu + log(pop),
                    data = wdi,
                    index = c("country", "year"), 
                    model = "within")

stargazer(ols, fe, fe_ols, fe_plm, type = "html", column.labels = c("OLS", "FE", "FE", "FE"), model.names = FALSE,
          dep.var.caption = "",
          title = "Panel Data Results", 
          #omit = c("country", "year"),  #So, if we want to remove the fixed effects or estimates, we can use the option, omit (another way to do this is keep, but that has issues with the constant) 
          covariate.labels = c("Edu", "lnPop", "Constant"),
          dep.var.labels   = "GDP per capita",
          add.lines=list(c("FE", "No", "Yes", "Yes", "Yes")),
          out = "panel_results_long.html")
## 
## <table style="text-align:center"><caption><strong>Panel Data Results</strong></caption>
## <tr><td colspan="5" style="border-bottom: 1px solid black"></td></tr><tr><td style="text-align:left"></td><td colspan="4">GDP per capita</td></tr>
## <tr><td style="text-align:left"></td><td>OLS</td><td>FE</td><td>FE</td><td>FE</td></tr>
## <tr><td style="text-align:left"></td><td>(1)</td><td>(2)</td><td>(3)</td><td>(4)</td></tr>
## <tr><td colspan="5" style="border-bottom: 1px solid black"></td></tr><tr><td style="text-align:left">Edu</td><td>-0.060<sup>***</sup></td><td>-0.109<sup>***</sup></td><td>-0.013</td><td>-0.109<sup>***</sup></td></tr>
## <tr><td style="text-align:left"></td><td>(0.007)</td><td>(0.038)</td><td>(0.035)</td><td>(0.038)</td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">lnPop</td><td>-0.185<sup>**</sup></td><td>-10.776<sup>***</sup></td><td>-6.210<sup>***</sup></td><td>-10.776<sup>***</sup></td></tr>
## <tr><td style="text-align:left"></td><td>(0.082)</td><td>(1.883)</td><td>(1.648)</td><td>(1.883)</td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">Constant</td><td></td><td></td><td>10.710<sup>**</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.209)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Andorra</td><td></td><td></td><td>-23.533<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(6.359)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Angola</td><td></td><td></td><td>13.197<sup>**</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.654)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Argentina</td><td></td><td></td><td>13.427<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.106)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Armenia</td><td></td><td></td><td>0.168</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.007)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Aruba</td><td></td><td></td><td>-25.864<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(6.188)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Australia</td><td></td><td></td><td>10.603<sup>**</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.141)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Azerbaijan</td><td></td><td></td><td>7.225<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.484)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Bahamas, The</td><td></td><td></td><td>-17.290<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.406)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Bahrain</td><td></td><td></td><td>-7.219<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.384)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Bangladesh</td><td></td><td></td><td>26.264<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(7.332)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Barbados</td><td></td><td></td><td>-18.556<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.130)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Belarus</td><td></td><td></td><td>5.703<sup>*</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.168)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Belgium</td><td></td><td></td><td>4.754<sup>*</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.748)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Belize</td><td></td><td></td><td>-20.067<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.209)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Bhutan</td><td></td><td></td><td>-9.230<sup>**</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.766)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Bolivia</td><td></td><td></td><td>6.180<sup>*</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.379)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Bosnia and Herzegovina</td><td></td><td></td><td>-1.674</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.990)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Brazil</td><td></td><td></td><td>22.752<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(7.367)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Brunei Darussalam</td><td></td><td></td><td>-14.191<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.683)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Bulgaria</td><td></td><td></td><td>5.725</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.773)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Burkina Faso</td><td></td><td></td><td>8.637</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.252)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Burundi</td><td></td><td></td><td>4.565</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.835)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Cabo Verde</td><td></td><td></td><td>-14.911<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.313)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Cambodia</td><td></td><td></td><td>10.717<sup>**</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.478)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Cameroon</td><td></td><td></td><td>8.154</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.449)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Canada</td><td></td><td></td><td>12.125<sup>**</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.147)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Cayman Islands</td><td></td><td></td><td>-28.284<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(6.978)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Chad</td><td></td><td></td><td>21.635<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.910)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Chile</td><td></td><td></td><td>9.221<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.515)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Colombia</td><td></td><td></td><td>15.547<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.070)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Congo, Dem. Rep.</td><td></td><td></td><td>20.583<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(6.417)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Costa Rica</td><td></td><td></td><td>1.960</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.037)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Cote d'Ivoire</td><td></td><td></td><td>16.618<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.619)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Croatia</td><td></td><td></td><td>-1.105</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.657)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Cuba</td><td></td><td></td><td>6.291<sup>*</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.434)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Curacao</td><td></td><td></td><td>-33.784<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(6.058)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Cyprus</td><td></td><td></td><td>-9.165<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.330)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Czechia</td><td></td><td></td><td>5.459<sup>**</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.618)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Denmark</td><td></td><td></td><td>-0.514</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.660)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Dominica</td><td></td><td></td><td>-27.858<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(6.967)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Dominican Republic</td><td></td><td></td><td>7.836<sup>**</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.151)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Ecuador</td><td></td><td></td><td>8.341<sup>**</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.419)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Egypt, Arab Rep.</td><td></td><td></td><td>20.092<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(7.050)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)El Salvador</td><td></td><td></td><td>1.128</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.730)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Estonia</td><td></td><td></td><td>-2.482</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.973)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Ethiopia</td><td></td><td></td><td>24.960<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(7.307)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Fiji</td><td></td><td></td><td>-15.892<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.824)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)France</td><td></td><td></td><td>15.344<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.303)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)French Polynesia</td><td></td><td></td><td>-21.950<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.121)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Gambia, The</td><td></td><td></td><td>-3.295</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.848)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Georgia</td><td></td><td></td><td>1.842</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.964)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Germany</td><td></td><td></td><td>17.015<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.632)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Ghana</td><td></td><td></td><td>15.076<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.242)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Greece</td><td></td><td></td><td>2.731</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.796)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Greenland</td><td></td><td></td><td>-28.183<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(7.207)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Guatemala</td><td></td><td></td><td>8.178<sup>*</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.199)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Guinea</td><td></td><td></td><td>7.594</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.855)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Guyana</td><td></td><td></td><td>-11.605<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.010)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Honduras</td><td></td><td></td><td>5.222</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.180)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Hong Kong SAR, China</td><td></td><td></td><td>3.534</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.289)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Hungary</td><td></td><td></td><td>6.043<sup>**</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.665)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)India</td><td></td><td></td><td>36.518<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(10.787)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Indonesia</td><td></td><td></td><td>27.789<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(7.730)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Iraq</td><td></td><td></td><td>18.103<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.427)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Israel</td><td></td><td></td><td>4.831<sup>**</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.351)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Italy</td><td></td><td></td><td>13.451<sup>**</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.218)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Japan</td><td></td><td></td><td>21.716<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(6.980)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Jordan</td><td></td><td></td><td>5.450<sup>*</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.781)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Kazakhstan</td><td></td><td></td><td>11.159<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.570)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Kenya</td><td></td><td></td><td>18.522<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.636)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Korea, Rep.</td><td></td><td></td><td>17.213<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.070)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Kuwait</td><td></td><td></td><td>-2.022</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.238)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Kyrgyz Republic</td><td></td><td></td><td>6.552<sup>*</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.479)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Latvia</td><td></td><td></td><td>-5.645<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.887)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Lebanon</td><td></td><td></td><td>4.688</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.545)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Lesotho</td><td></td><td></td><td>-3.136</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.750)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Liechtenstein</td><td></td><td></td><td>-32.577<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(8.130)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Lithuania</td><td></td><td></td><td>-1.294</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.706)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Luxembourg</td><td></td><td></td><td>-10.628<sup>**</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.486)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Macao SAR, China</td><td></td><td></td><td>-6.782<sup>*</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.455)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Madagascar</td><td></td><td></td><td>10.821<sup>*</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.525)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Malaysia</td><td></td><td></td><td>13.907<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.240)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Maldives</td><td></td><td></td><td>4.781</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.797)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Mali</td><td></td><td></td><td>10.668<sup>**</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.206)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Malta</td><td></td><td></td><td>-11.640<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.670)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Marshall Islands</td><td></td><td></td><td>-30.757<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(7.475)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Mauritania</td><td></td><td></td><td>0.043</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.138)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Mauritius</td><td></td><td></td><td>-6.524<sup>**</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.000)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Mexico</td><td></td><td></td><td>19.317<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(6.480)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Moldova</td><td></td><td></td><td>-1.545</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.764)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Mongolia</td><td></td><td></td><td>-2.995</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.318)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Montenegro</td><td></td><td></td><td>-11.961<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.717)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Mozambique</td><td></td><td></td><td>14.732<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.171)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Myanmar</td><td></td><td></td><td>19.631<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(6.188)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Namibia</td><td></td><td></td><td>-6.589<sup>*</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.630)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Nepal</td><td></td><td></td><td>11.991<sup>**</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.380)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Netherlands</td><td></td><td></td><td>7.064<sup>**</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.254)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Niger</td><td></td><td></td><td>16.408<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.811)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Nigeria</td><td></td><td></td><td>23.051<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(7.722)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)North Macedonia</td><td></td><td></td><td>-5.230<sup>*</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.709)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Norway</td><td></td><td></td><td>-0.312</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.997)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Oman</td><td></td><td></td><td>-1.566</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.179)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Pakistan</td><td></td><td></td><td>24.733<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(7.888)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Palau</td><td></td><td></td><td>-39.852<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(9.173)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Panama</td><td></td><td></td><td>-1.259</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.392)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Paraguay</td><td></td><td></td><td>2.878</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.356)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Peru</td><td></td><td></td><td>14.369<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.380)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Philippines</td><td></td><td></td><td>21.694<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(6.183)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Poland</td><td></td><td></td><td>14.689<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.474)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Portugal</td><td></td><td></td><td>3.358</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.709)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Puerto Rico</td><td></td><td></td><td>-4.459<sup>*</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.337)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Qatar</td><td></td><td></td><td>2.002</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.971)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Romania</td><td></td><td></td><td>10.454<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.515)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Russian Federation</td><td></td><td></td><td>23.891<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(6.826)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Rwanda</td><td></td><td></td><td>10.631<sup>**</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.259)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Samoa</td><td></td><td></td><td>-16.265<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.231)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)San Marino</td><td></td><td></td><td>-31.686<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(8.232)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Sao Tome and Principe</td><td></td><td></td><td>-18.317<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.602)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Saudi Arabia</td><td></td><td></td><td>11.591<sup>**</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.516)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Senegal</td><td></td><td></td><td>6.220</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.654)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Serbia</td><td></td><td></td><td>3.356</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.307)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Seychelles</td><td></td><td></td><td>-24.891<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(6.873)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Sierra Leone</td><td></td><td></td><td>1.442</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.563)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Singapore</td><td></td><td></td><td>3.377<sup>*</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.999)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Slovak Republic</td><td></td><td></td><td>1.711</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.971)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Slovenia</td><td></td><td></td><td>-5.398<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.876)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)South Africa</td><td></td><td></td><td>15.176<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.232)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Spain</td><td></td><td></td><td>12.717<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.872)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Sri Lanka</td><td></td><td></td><td>5.553</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.673)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)St. Vincent and the Grenadines</td><td></td><td></td><td>-24.027<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(6.508)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Suriname</td><td></td><td></td><td>-11.339<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.772)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Sweden</td><td></td><td></td><td>4.359<sup>*</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.491)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Switzerland</td><td></td><td></td><td>3.446</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.373)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Syrian Arab Republic</td><td></td><td></td><td>12.223<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.333)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Tajikistan</td><td></td><td></td><td>5.116</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.697)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Tanzania</td><td></td><td></td><td>17.608<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.564)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Thailand</td><td></td><td></td><td>17.858<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.980)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Togo</td><td></td><td></td><td>5.222</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.482)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Tonga</td><td></td><td></td><td>-19.235<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(6.446)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Trinidad and Tobago</td><td></td><td></td><td>-7.978<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.874)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Turkiye</td><td></td><td></td><td>20.205<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.684)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Uganda</td><td></td><td></td><td>15.558<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.361)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Ukraine</td><td></td><td></td><td>21.909<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.741)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)United Arab Emirates</td><td></td><td></td><td>3.508</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(2.625)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)United Kingdom</td><td></td><td></td><td>15.373<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(5.274)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)United States</td><td></td><td></td><td>26.055<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(7.776)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Uruguay</td><td></td><td></td><td>-0.807</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.737)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Uzbekistan</td><td></td><td></td><td>15.552<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.613)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Venezuela, RB</td><td></td><td></td><td>13.944<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(4.443)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Vietnam</td><td></td><td></td><td>24.226<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(6.641)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)West Bank and Gaza</td><td></td><td></td><td>1.801</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.763)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(country)Zimbabwe</td><td></td><td></td><td>7.767<sup>**</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(3.452)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(year)2001</td><td></td><td></td><td>-3.595<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.287)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(year)2002</td><td></td><td></td><td>-3.948<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.320)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(year)2003</td><td></td><td></td><td>-3.210<sup>**</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.500)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(year)2004</td><td></td><td></td><td>0.224</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.122)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(year)2005</td><td></td><td></td><td>-1.930<sup>*</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.096)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(year)2006</td><td></td><td></td><td>-1.199</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.078)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(year)2007</td><td></td><td></td><td>-0.470</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.063)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(year)2008</td><td></td><td></td><td>-2.371<sup>**</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.057)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(year)2009</td><td></td><td></td><td>-7.814<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.056)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(year)2010</td><td></td><td></td><td>-2.065<sup>**</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.017)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(year)2011</td><td></td><td></td><td>-2.417<sup>**</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.048)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(year)2012</td><td></td><td></td><td>-3.584<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.059)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(year)2013</td><td></td><td></td><td>-3.145<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.078)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(year)2014</td><td></td><td></td><td>-3.159<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.071)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(year)2015</td><td></td><td></td><td>-2.950<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.075)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(year)2016</td><td></td><td></td><td>-3.286<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.087)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(year)2017</td><td></td><td></td><td>-2.954<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.115)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(year)2018</td><td></td><td></td><td>-2.410<sup>**</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.135)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(year)2019</td><td></td><td></td><td>-3.255<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.133)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">factor(year)2020</td><td></td><td></td><td>-10.818<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td>(1.135)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td style="text-align:left">Constant</td><td>11.164<sup>***</sup></td><td></td><td>101.630<sup>***</sup></td><td></td></tr>
## <tr><td style="text-align:left"></td><td>(1.570)</td><td></td><td>(23.505)</td><td></td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td></tr>
## <tr><td colspan="5" style="border-bottom: 1px solid black"></td></tr><tr><td style="text-align:left">FE</td><td>No</td><td>Yes</td><td>Yes</td><td>Yes</td></tr>
## <tr><td style="text-align:left">Observations</td><td>847</td><td>847</td><td>847</td><td>847</td></tr>
## <tr><td style="text-align:left">R<sup>2</sup></td><td>0.078</td><td>0.115</td><td>0.636</td><td>0.115</td></tr>
## <tr><td style="text-align:left">Adjusted R<sup>2</sup></td><td>0.075</td><td>-0.083</td><td>0.541</td><td>-0.083</td></tr>
## <tr><td style="text-align:left">Residual Std. Error</td><td>4.203 (df = 844)</td><td></td><td>2.962 (df = 671)</td><td></td></tr>
## <tr><td style="text-align:left">F Statistic</td><td>35.492<sup>***</sup> (df = 2; 844)</td><td>44.996<sup>***</sup> (df = 2; 691)</td><td>6.693<sup>***</sup> (df = 175; 671)</td><td>44.996<sup>***</sup> (df = 2; 691)</td></tr>
## <tr><td colspan="5" style="border-bottom: 1px solid black"></td></tr><tr><td style="text-align:left"><em>Note:</em></td><td colspan="4" style="text-align:right"><sup>*</sup>p<0.1; <sup>**</sup>p<0.05; <sup>***</sup>p<0.01</td></tr>
## </table>